© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 36542
    Prev
    Next
    INDEX
    Explanations

    white Russian cocktails

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trot
    -0.10
    orizontal
    -0.09
    tee
    -0.09
     unary
    -0.09
     Forbidden
    -0.09
     pil
    -0.09
    elry
    -0.08
     Grü
    -0.08
     equipments
    -0.08
     Ward
    -0.08
    POSITIVE LOGITS
     Tar
    0.19
     Quentin
    0.16
    Tar
    0.16
     Uma
    0.16
    antino
    0.15
     Royale
    0.15
     pulp
    0.15
     Neo
    0.14
     QT
    0.14
    ulp
    0.14
    Activations Density 0.028%

    No Known Activations